Manual Backport PR #47905 on branch 1.4.x (BUG: Fix read_xml raising syntax error when reading XML with Chinese tags)

.circleci/config.yml

@@ -8,7 +8,7 @@ jobs:
     environment:
       ENV_FILE: ci/deps/circle-38-arm64.yaml
       PYTEST_WORKERS: auto
-      PATTERN: "not slow and not network and not clipboard and not arm_slow"
+      PATTERN: "not single_cpu and not slow and not network and not clipboard and not arm_slow and not db"
       PYTEST_TARGET: "pandas"
     steps:
       - checkout

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -17,7 +17,7 @@ body:
             [latest version](https://pandas.pydata.org/docs/whatsnew/index.html) of pandas.
           required: true
         - label: >
-            I have confirmed this bug exists on the master branch of pandas.
+            I have confirmed this bug exists on the main branch of pandas.
   - type: textarea
     id: example
     attributes:

.github/ISSUE_TEMPLATE/documentation_improvement.yaml

@@ -10,7 +10,7 @@ body:
       options:
         - label: >
             I have checked that the issue still exists on the latest versions of the docs
-            on `master` [here](https://pandas.pydata.org/docs/dev/)
+            on `main` [here](https://pandas.pydata.org/docs/dev/)
           required: true
   - type: textarea
     id: location

.github/ISSUE_TEMPLATE/performance_issue.yaml

@@ -17,7 +17,7 @@ body:
             [latest version](https://pandas.pydata.org/docs/whatsnew/index.html) of pandas.
           required: true
         - label: >
-            I have confirmed this issue exists on the master branch of pandas.
+            I have confirmed this issue exists on the main branch of pandas.
   - type: textarea
     id: example
     attributes:

.github/actions/build_pandas/action.yml

@@ -8,10 +8,13 @@ runs:
       run: |
         conda info
         conda list
-      shell: bash -l {0}
+      shell: bash -el {0}
 
     - name: Build Pandas
       run: |
-        python setup.py build_ext -j 2
+        python setup.py build_ext -j $N_JOBS
         python -m pip install -e . --no-build-isolation --no-use-pep517 --no-index
-      shell: bash -l {0}
+      shell: bash -el {0}
+      env:
+        # Cannot use parallel compilation on Windows, see https://github.com/pandas-dev/pandas/issues/30873
+        N_JOBS: ${{ runner.os == 'Windows' && 1 || 2 }}

.github/actions/setup/action.yml

@@ -5,8 +5,8 @@ runs:
   steps:
     - name: Setting conda path
       run: echo "${HOME}/miniconda3/bin" >> $GITHUB_PATH
-      shell: bash -l {0}
+      shell: bash -el {0}
 
     - name: Setup environment and build pandas
       run: ci/setup_env.sh
-      shell: bash -l {0}
+      shell: bash -el {0}

.github/workflows/32-bit-linux.yml

@@ -0,0 +1,49 @@
+name: 32 Bit Linux
+
+on:
+  push:
+    branches:
+      - main
+      - 1.4.x
+  pull_request:
+    branches:
+      - main
+      - 1.4.x
+    paths-ignore:
+      - "doc/**"
+
+jobs:
+  pytest:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Run 32-bit manylinux2014 Docker Build / Tests
+        run: |
+          # Without this (line 34), versioneer will not be able to determine the pandas version.
+          # This is because of a security update to git that blocks it from reading the config folder if
+          # it is not owned by the current user. We hit this since the "mounted" folder is not hit by the
+          # Docker container.
+          # xref https://github.com/pypa/manylinux/issues/1309
+          docker pull quay.io/pypa/manylinux2014_i686
+          docker run --platform linux/386 -v $(pwd):/pandas quay.io/pypa/manylinux2014_i686 \
+          /bin/bash -xc "cd pandas && \
+          git config --global --add safe.directory /pandas && \
+          /opt/python/cp38-cp38/bin/python -m venv ~/virtualenvs/pandas-dev && \
+          . ~/virtualenvs/pandas-dev/bin/activate && \
+          python -m pip install --no-deps -U pip wheel 'setuptools<60.0.0' && \
+          pip install cython numpy python-dateutil pytz pytest pytest-xdist pytest-asyncio>=0.17 hypothesis && \
+          python setup.py build_ext -q -j2 && \
+          python -m pip install --no-build-isolation --no-use-pep517 -e . && \
+          export PANDAS_CI=1 && \
+          pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml"
+
+      - name: Publish test results for Python 3.8-32 bit full Linux
+        uses: actions/upload-artifact@v3
+        with:
+          name: Test results
+          path: test-data.xml
+        if: failure()

.github/workflows/assign.yml

@@ -4,11 +4,10 @@ on:
     types: created
 
 jobs:
-  one:
+  issue_assign:
     runs-on: ubuntu-latest
     steps:
     - if: github.event.comment.body == 'take'
-      name:
       run: |
         echo "Assigning issue ${{ github.event.issue.number }} to ${{ github.event.comment.user.login }}"
         curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"assignees": ["${{ github.event.comment.user.login }}"]}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/assignees

.github/workflows/asv-bot.yml

@@ -17,7 +17,7 @@ jobs:
     runs-on: ubuntu-latest
     defaults:
       run:
-        shell: bash -l {0}
+        shell: bash -el {0}
 
     concurrency:
       # Set concurrency to prevent abuse(full runs are ~5.5 hours !!!)
@@ -29,19 +29,19 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0
 
       - name: Cache conda
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: ~/conda_pkgs_dir
           key: ${{ runner.os }}-conda-${{ hashFiles('${{ env.ENV_FILE }}') }}
 
         # Although asv sets up its own env, deps are still needed
         # during discovery process
-      - uses: conda-incubator/setup-miniconda@v2
+      - uses: conda-incubator/setup-miniconda@v2.1.1
         with:
           activate-environment: pandas-dev
           channel-priority: strict
@@ -59,21 +59,21 @@ jobs:
           git remote add upstream https://github.com/pandas-dev/pandas.git
           git fetch upstream
           asv machine --yes
-          asv continuous -f 1.1 -b $REGEX upstream/master HEAD
+          asv continuous -f 1.1 -b $REGEX upstream/main HEAD
           echo 'BENCH_OUTPUT<<EOF' >> $GITHUB_ENV
-          asv compare -f 1.1 upstream/master HEAD >> $GITHUB_ENV
+          asv compare -f 1.1 upstream/main HEAD >> $GITHUB_ENV
           echo 'EOF' >> $GITHUB_ENV
           echo "REGEX=$REGEX" >> $GITHUB_ENV
 
-      - uses: actions/github-script@v4
+      - uses: actions/github-script@v6
         env:
           BENCH_OUTPUT: ${{env.BENCH_OUTPUT}}
           REGEX: ${{env.REGEX}}
         with:
           script: |
             const ENV_VARS = process.env
             const run_url = `https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`
-            github.issues.createComment({
+            github.rest.issues.createComment({
               issue_number: context.issue.number,
               owner: context.repo.owner,
               repo: context.repo.repo,

.github/workflows/autoupdate-pre-commit-config.yml

@@ -12,9 +12,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v3
       - name: Cache multiple paths
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: |
             ~/.cache/pre-commit

.github/workflows/code-checks.yml

@@ -3,12 +3,12 @@ name: Code Checks
 on:
   push:
     branches:
-      - master
-      - 1.3.x
+      - main
+      - 1.4.x
   pull_request:
     branches:
-      - master
-      - 1.3.x
+      - main
+      - 1.4.x
 
 env:
   ENV_FILE: environment.yml
@@ -24,10 +24,10 @@ jobs:
       cancel-in-progress: true
     steps:
     - name: Checkout
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
 
     - name: Install Python
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v3
       with:
         python-version: '3.9.7'
 
@@ -39,7 +39,7 @@ jobs:
     runs-on: ubuntu-latest
     defaults:
       run:
-        shell: bash -l {0}
+        shell: bash -el {0}
 
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
@@ -48,17 +48,17 @@ jobs:
 
     steps:
     - name: Checkout
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         fetch-depth: 0
 
     - name: Cache conda
-      uses: actions/cache@v2
+      uses: actions/cache@v3
       with:
         path: ~/conda_pkgs_dir
         key: ${{ runner.os }}-conda-${{ hashFiles('${{ env.ENV_FILE }}') }}
 
-    - uses: conda-incubator/setup-miniconda@v2
+    - uses: conda-incubator/setup-miniconda@v2.1.1
       with:
         mamba-version: "*"
         channels: conda-forge
@@ -68,7 +68,7 @@ jobs:
         use-only-tar-bz2: true
 
     - name: Install node.js (for pyright)
-      uses: actions/setup-node@v2
+      uses: actions/setup-node@v3
       with:
         node-version: "16"
 
@@ -105,7 +105,7 @@ jobs:
     runs-on: ubuntu-latest
     defaults:
       run:
-        shell: bash -l {0}
+        shell: bash -el {0}
 
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
@@ -114,17 +114,17 @@ jobs:
 
     steps:
     - name: Checkout
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         fetch-depth: 0
 
     - name: Cache conda
-      uses: actions/cache@v2
+      uses: actions/cache@v3
       with:
         path: ~/conda_pkgs_dir
         key: ${{ runner.os }}-conda-${{ hashFiles('${{ env.ENV_FILE }}') }}
 
-    - uses: conda-incubator/setup-miniconda@v2
+    - uses: conda-incubator/setup-miniconda@v2.1.1
       with:
         mamba-version: "*"
         channels: conda-forge
@@ -140,19 +140,29 @@ jobs:
     - name: Run ASV benchmarks
       run: |
         cd asv_bench
-        asv check -E existing
-        git remote add upstream https://github.com/pandas-dev/pandas.git
-        git fetch upstream
         asv machine --yes
-        asv dev | sed "/failed$/ s/^/##[error]/" | tee benchmarks.log
-        if grep "failed" benchmarks.log > /dev/null ; then
-            exit 1
-        fi
-      if: ${{ steps.build.outcome == 'success' }}
+        asv run --quick --dry-run --strict --durations=30 --python=same
 
-    - name: Publish benchmarks artifact
-      uses: actions/upload-artifact@master
-      with:
-        name: Benchmarks log
-        path: asv_bench/benchmarks.log
-      if: failure()
+  build_docker_dev_environment:
+    name: Build Docker Dev Environment
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash -el {0}
+
+    concurrency:
+      # https://github.community/t/concurrecy-not-work-for-push/183068/7
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-build_docker_dev_environment
+      cancel-in-progress: true
+
+    steps:
+      - name: Clean up dangling images
+        run: docker image prune -f
+
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Build image
+        run: docker build --pull --no-cache --tag pandas-dev-env .

.github/workflows/comment_bot.yml

@@ -12,29 +12,29 @@ jobs:
     if: startsWith(github.event.comment.body, '@github-actions pre-commit')
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: r-lib/actions/pr-fetch@master
+      - uses: actions/checkout@v3
+      - uses: r-lib/actions/pr-fetch@v2
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
       - name: Cache multiple paths
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: |
             ~/.cache/pre-commit
             ~/.cache/pip
           key: pre-commit-dispatched-${{ runner.os }}-build
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v3
         with:
           python-version: 3.8
       - name: Install-pre-commit
         run: python -m pip install --upgrade pre-commit
       - name: Run pre-commit
-        run: pre-commit run --from-ref=origin/master --to-ref=HEAD --all-files || (exit 0)
+        run: pre-commit run --from-ref=origin/main --to-ref=HEAD --all-files || (exit 0)
       - name: Commit results
         run: |
           git config user.name "$(git log -1 --pretty=format:%an)"
           git config user.email "$(git log -1 --pretty=format:%ae)"
           git commit -a -m 'Fixes from pre-commit [automated commit]' || echo "No changes to commit"
-      - uses: r-lib/actions/pr-push@master
+      - uses: r-lib/actions/pr-push@v2
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}